典型文献
Image-based traffic signal control via world models
文献摘要：
Traffic signal control is shifting from passive control to proactive control,which enables the controller to direct current traffic flow to reach its expected destinations.To this end,an effective prediction model is needed for signal controllers.What to predict,how to predict,and how to leverage the prediction for control policy optimization are critical problems for proactive traffic signal control.In this paper,we use an image that contains vehicle positions to describe intersection traffic states.Then,inspired by a model-based reinforcement learning method,DreamerV2,we introduce a novel learning-based traffic world model.The traffic world model that describes traffic dynamics in image form is used as an abstract alternative to the traffic environment to generate multi-step planning data for control policy optimization.In the execution phase,the optimized traffic controller directly outputs actions in real time based on abstract representations of traffic states,and the world model can also predict the impact of different control behaviors on future traffic conditions.Experimental results indicate that the traffic world model enables the optimized real-time control policy to outperform common baselines,and the model achieves accurate image-based prediction,showing promising applications in futuristic traffic signal control.
文献关键词：
中图分类号：
作者姓名：
Xingyuan DAI;Chen ZHAO;Xiao WANG;Yisheng LV;Yilun LIN;Fei-Yue WANG
作者机构：
The State Key Laboratory for Management and Control of Complex Systems,Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China;School of Artificial Intelligence,University of Chinese Academy of Sciences,Beijing 1000f9,China;School of Artificial Intelligence,Anhui University,Hefei 230039,China;Shanghai AI Laboratory,Shanghai 200232,China
文献出处：
引用格式：
[1]Xingyuan DAI;Chen ZHAO;Xiao WANG;Yisheng LV;Yilun LIN;Fei-Yue WANG-.Image-based traffic signal control via world models)[J].信息与电子工程前沿（英文）,2022(12):1795-1813
A类：
DreamerV2,futuristic
B类：
Image,traffic,signal,via,world,models,Traffic,shifting,from,passive,proactive,which,enables,current,flow,reach,its,expected,destinations,To,this,end,effective,prediction,needed,controllers,What,leverage,policy,optimization,are,critical,problems,In,paper,we,image,that,contains,vehicle,positions,intersection,states,Then,inspired,by,reinforcement,learning,method,introduce,novel,describes,dynamics,used,abstract,alternative,environment,generate,multi,step,planning,data,execution,phase,optimized,directly,outputs,actions,real,representations,can,also,impact,different,behaviors,future,conditions,Experimental,results,indicate,outperform,common,baselines,achieves,accurate,showing,promising,applications
AB值：
0.48494
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
